{
  "architecture": "BigramLanguageModel",
  "architecture_description": "Token + position embeddings -> n_layer stacked transformer blocks (pre-norm multi-head causal self-attention + feedforward, residual connections) -> final LayerNorm -> linear head to vocab logits.",
  "vocab_size": 65,
  "n_embd": 128,
  "n_head": 4,
  "n_layer": 4,
  "block_size": 32,
  "tokenizer_type": "char",
  "tokenizer_file": "tokenizer_char.json",
  "weights_file": "model.safetensors",
  "training": {
    "dataset": "tinyshakespeare.txt",
    "batch_size": 32,
    "learning_rate": 0.001,
    "max_iters": 8000,
    "seed": 1337
  },
  "parameter_count": 812609
}